© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92049
    Prev
    Next
    INDEX
    Explanations

    plaintiff

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nevertheless
    -0.67
     granddaughter
    -0.66
     nakalista
    -0.65
     חיצוניים
    -0.60
    Fortunately
    -0.59
    GraphicsUnit
    -0.58
    存于互联网档案馆
    -0.58
     %>%
    -0.58
    abestanden
    -0.56
    STIC
    -0.55
    POSITIVE LOGITS
    aarrggbb
    0.59
    את
    0.55
    politan
    0.53
    PageContext
    0.52
    Bibliograf
    0.51
    rinfo
    0.50
    jsonwebtoken
    0.49
    BeginContext
    0.49
    awards
    0.48
    +#+
    0.47
    Activations Density 0.261%

    No Known Activations